© 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. 4-CLT-HP
    7. 680
    Prev
    Next
    INDEX
    Explanations

    official actions

    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
     समीक्षक
    -0.69
     Vikipedi
    -0.65
    DebuggerNonUser
    -0.64
    GEBURTSDATUM
    -0.63
     صوتيه
    -0.63
    tagHelperRunner
    -0.60
    மாக
    -0.59
    interopRequire
    -0.57
     EventArgs
    -0.57
     ExecuteAsync
    -0.56
    POSITIVE LOGITS
     its
    0.96
     itself
    0.91
    itself
    0.65
     Itself
    0.60
     itſelf
    0.59
    其
    0.56
    Its
    0.56
     Its
    0.55
     her
    0.52
    ">:
    0.52
    Activations Density 0.002%

    No Known Activations