© 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. 5-CLT-HP
    7. 92715
    Prev
    Next
    INDEX
    Explanations

    Forget

    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
    MLLoader
    -0.68
    RenderAtEndOf
    -0.60
    enterOuterAlt
    -0.58
    $_['
    -0.54
    AutoScaleMode
    -0.54
    IARC
    -0.52
     виправивши
    -0.52
    SDR
    -0.52
    Autoritní
    -0.52
    FCA
    -0.52
    POSITIVE LOGITS
    IntoConstraints
    0.65
     Knot
    0.59
    not
    0.53
     Seil
    0.53
     knots
    0.53
     Kalt
    0.52
     NXT
    0.52
     nemat
    0.50
    knot
    0.50
    mitives
    0.49
    Activations Density 0.015%

    No Known Activations