© 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. 1-CLT-HP
    7. 9524
    Prev
    Next
    INDEX
    Explanations

    )

    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
     BorderSide
    -0.41
    ,
    -0.36
     root
    -0.35
    weit
    -0.35
    etar
    -0.34
    hed
    -0.34
     eu
    -0.34
    didSet
    -0.34
    los
    -0.34
     matter
    -0.34
    POSITIVE LOGITS
    <bos>
    1.09
     Theſe
    0.79
     purpoſe
    0.75
     Monfieur
    0.74
    ↵↵
    0.74
     Diſ
    0.73
    ↵
    0.73
     Jefus
    0.72
     Chrift
    0.71
     Chriſt
    0.69
    Activations Density 0.017%

    No Known Activations