© 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. 724
    Prev
    Next
    INDEX
    Explanations

    want

    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
     censi
    -0.73
     دیکھیے
    -0.69
    AndEndTag
    -0.67
     Roskov
    -0.64
    Personendaten
    -0.60
    XmlAccessorType
    -0.60
    jsxFileName
    -0.56
    حوالہ
    -0.55
    archiviato
    -0.52
     ApiException
    -0.52
    POSITIVE LOGITS
    /*
    0.71
    <?
    0.58
    <bos>
    0.56
    ]')
    0.54
    enumi
    0.54
    )։
    0.54
     épais
    0.53
    .*")]
    0.53
    ++){
    0.53
    ++)
    0.52
    Activations Density 0.040%

    No Known Activations