© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11331
    Prev
    Next
    INDEX
    Explanations

    the word "hurt"

    oai_token-act-pair · gemini-2.0-flash

    hurt

    np_max-act · gemini-2.0-flash

    hurt

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     hurt
    -0.99
     alter
    -0.81
     harm
    -0.78
     harms
    -0.77
     harmed
    -0.75
    hurt
    -0.67
     Harm
    -0.65
     bothered
    -0.63
     Alter
    -0.63
    <bos>
    -0.63
    POSITIVE LOGITS
    setVerticalGroup
    0.81
     CreateTagHelper
    0.60
    Carriera
    0.58
     Erişim
    0.57
    postsleuth
    0.56
     autorytatywna
    0.56
    umman
    0.55
     مرئيه
    0.54
    CodedInputStream
    0.51
     виправивши
    0.50
    Activations Density 0.467%

    No Known Activations