© 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. 0-CLT-HP
    7. 92005
    Prev
    Next
    INDEX
    Explanations

    utors

    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
    utors
    -1.40
    ExtendWith
    -0.57
     peindre
    -0.56
    WebElementEntity
    -0.55
     MessageBoxIcon
    -0.52
    ）』
    -0.52
    handleSubmit
    -0.51
    {?>
    -0.51
    ($__
    -0.51
    เอง
    -0.50
    POSITIVE LOGITS
     виправивши
    0.79
    GOTREF
    0.60
    msgTypes
    0.58
     estekak
    0.54
    ness
    0.53
     péri
    0.53
     vVar
    0.53
     iVar
    0.52
     POW
    0.52
    idity
    0.52
    Activations Density 0.136%

    No Known Activations