© 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. 0-CLT-HP
    7. 42672
    Prev
    Next
    INDEX
    Explanations

    when

    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
    UnsafeEnabled
    -0.81
    <bos>
    -0.78
    VersionUID
    -0.75
    Билгалдахарш
    -0.69
     '\\;'
    -0.65
    AutoresizingMask
    -0.64
    RefNanny
    -0.62
    RectangleBorder
    -0.62
    ]));
    -0.61
     ProtoMessage
    -0.59
    POSITIVE LOGITS
    they
    0.57
    nestjs
    0.51
    They
    0.49
    OrWhiteSpace
    0.49
     they
    0.47
    InvalidProtocol
    0.43
     ferons
    0.43
     daarvan
    0.43
     :)))
    0.43
     :))
    0.42
    Activations Density 0.024%

    No Known Activations