© 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. 5-CLT-HP
    7. 96965
    Prev
    Next
    INDEX
    Explanations

    the, of

    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
    HostException
    -0.54
    <?>>
    -0.53
    Sous
    -0.53
    iläum
    -0.52
     initComponents
    -0.52
    pushFollow
    -0.52
     ब्रेकडाउन
    -0.51
    EnableWeb
    -0.51
    :✨
    -0.51
     khảo
    -0.50
    POSITIVE LOGITS
    argout
    0.51
    ensore
    0.50
    edicated
    0.50
    municipi
    0.49
    motiv
    0.49
    Datuak
    0.48
    جموع
    0.48
    inhua
    0.46
     виправивши
    0.46
     Wiktionnaire
    0.45
    Activations Density 0.001%

    No Known Activations