© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76060
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · 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
    tagHelperRunner
    -1.13
    SharedDtor
    -0.89
     newOwner
    -0.81
     defaultstate
    -0.78
    下载附件
    -0.74
     Référence
    -0.72
     مرئيه
    -0.72
    ScopeManager
    -0.70
     Comprometido
    -0.70
    TagMode
    -0.69
    POSITIVE LOGITS
     AL
    0.46
    Xna
    0.39
     Sp
    0.37
     sp
    0.37
     che
    0.36
    AL
    0.34
    弦
    0.33
     W
    0.33
    aré
    0.33
    vro
    0.33
    Activations Density 0.000%

    No Known Activations