© 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. 20-CLT-HP
    7. 72331
    Prev
    Next
    INDEX
    Explanations

    which

    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
    RenderAtEndOf
    -0.85
    SPATH
    -0.82
    MigrationBuilder
    -0.77
     صوتيه
    -0.77
    BufferException
    -0.76
     ویکی‌پدیای
    -0.74
    NameInMap
    -0.72
     ویکی‌پدیا
    -0.71
    (!__
    -0.70
     يتيمه
    -0.67
    POSITIVE LOGITS
    сре
    0.55
    วก
    0.53
     happen
    0.46
    ENDIF
    0.46
    READY
    0.45
     Anti
    0.44
     But
    0.42
     Var
    0.42
     Unfortunately
    0.41
     Ral
    0.41
    Activations Density 0.000%

    No Known Activations