© 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. 4961
    Prev
    Next
    INDEX
    Explanations

    candidate

    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
    <bos>
    -0.66
    mtrl
    -0.61
    }}}{\
    -0.60
    Портал
    -0.59
    oneofs
    -0.57
     predicted
    -0.54
    InvalidProtocol
    -0.54
    ",&
    -0.53
    createCanvas
    -0.52
     *__
    -0.50
    POSITIVE LOGITS
    anskje
    0.63
     parlant
    0.61
     speaking
    0.61
     discussing
    0.55
     Discuss
    0.54
     talking
    0.52
    Discuss
    0.51
     Efq
    0.50
     parlé
    0.49
     zelve
    0.49
    Activations Density 0.003%

    No Known Activations