© 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. 18-RES-MATRYOSHKA-DC
    7. 662
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.83
     Audiodateien
    -0.81
     initComponents
    -0.79
     дописавши
    -0.79
    IUrlHelper
    -0.77
    rédients
    -0.76
     defaultstate
    -0.76
    TagMode
    -0.73
    aktur
    -0.73
     snippetHide
    -0.72
    POSITIVE LOGITS
    SCA
    0.48
    ,
    0.47
    ("/{
    0.47
    C
    0.46
    b
    0.45
    toHexString
    0.44
     flüs
    0.43
     poliuret
    0.43
    mtext
    0.42
    z
    0.42
    Activations Density 1.860%

    No Known Activations