© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14261
    Prev
    Next
    INDEX
    Explanations

    Code/Documentation/Metadata

    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
     '\\;'
    -0.71
    aarrggbb
    -0.61
     actionMode
    -0.54
    <bos>
    -0.52
     JADX
    -0.51
     odonto
    -0.50
     الحره
    -0.50
    ]")]
    -0.50
    fromCharCode
    -0.49
     gallo
    -0.48
    POSITIVE LOGITS
    s
    0.82
     متعلقه
    0.68
    ся
    0.61
     snippetHide
    0.58
    agissait
    0.56
    nically
    0.52
     OFDb
    0.52
    single
    0.51
    gers
    0.51
    chaun
    0.50
    Activations Density 0.010%

    No Known Activations