Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 159
    Prev
    Next
    INDEX
    Explanations

    ve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    my
    -0.69
     my
    -0.63
    My
    -0.61
     My
    -0.60
    newswire
    -0.60
     mine
    -0.59
     I
    -0.56
     of
    -0.54
    stackSize
    -0.54
    ,
    -0.53
    POSITIVE LOGITS
     bezeichneter
    0.81
     raiſ
    0.64
     itſelf
    0.63
     forgotten
    0.62
     ſeveral
    0.60
     yourselves
    0.60
     cdti
    0.60
     auffi
    0.59
     doubted
    0.59
     uſed
    0.58
    Activations Density 0.164%

    No Known Activations