© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8504
    Prev
    Next
    INDEX
    Explanations

    uses of the word "null" in source code

    oai_token-act-pair · gemini-2.0-flash

    instances of 'null'

    np_token-act-pair-logits · gpt-4o-mini

    null

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.58
     ddelweddau
    -0.57
    XmlAccessType
    -0.57
    ValueGenerated
    -0.55
    XmlAccessorType
    -0.53
    IsContent
    -0.52
    sizeCache
    -0.52
    useNewUrlParser
    -0.50
     Bild
    -0.50
     ISNI
    -0.50
    POSITIVE LOGITS
     Audiodateien
    0.68
    uxxxx
    0.67
    下载附件
    0.64
     Partagez
    0.59
     مشين
    0.59
    +#+#
    0.57
    Geplaatst
    0.55
     protoimpl
    0.53
    Vidite
    0.52
     perpétu
    0.51
    Activations Density 0.225%

    No Known Activations