© 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. 42318
    Prev
    Next
    INDEX
    Explanations

    to

    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
    ,
    -0.63
    '
    -0.59
    .
    -0.57
    <eos>
    -0.51
    ↵
    -0.49
    (
    -0.44
    s
    -0.44
     will
    -0.44
    d
    -0.42
     (
    -0.42
    POSITIVE LOGITS
     Monfieur
    1.12
     Diſ
    1.10
     becauſe
    1.09
     Theſe
    1.09
     Efq
    1.09
     ſeveral
    1.06
     Anſ
    1.05
     houſe
    1.05
    ſelf
    1.02
    ^(@)
    1.01
    Activations Density 0.079%

    No Known Activations