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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13091
    Prev
    Next
    INDEX
    Explanations

    arc

    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
    <bos>
    -0.68
     useAppContext
    -0.63
     صوتيه
    -0.63
     հղումներ
    -0.58
    antMatchers
    -0.57
     autorytatywna
    -0.53
     kasarigan
    -0.52
     typelib
    -0.52
     OMIT
    -0.50
     esfera
    -0.48
    POSITIVE LOGITS
    DockStyle
    0.62
    WriteAttribute
    0.58
     Samaria
    0.56
     Pelop
    0.55
    ppuden
    0.55
     Shakspeare
    0.55
     juda
    0.54
    '][$
    0.53
    jScrollPane
    0.52
    igil
    0.51
    Activations Density 0.020%

    No Known Activations