© 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. 4354
    Prev
    Next
    INDEX
    Explanations

    overlooking problems

    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>
    -0.85
    [@"
    -0.52
    fireEvent
    -0.50
     CERTAIN
    -0.48
     nici
    -0.48
     freak
    -0.47
    "]();
    -0.47
     objection
    -0.47
    مصادر
    -0.46
    Freak
    -0.46
    POSITIVE LOGITS
     مشين
    0.69
    COUVER
    0.61
    +#+#
    0.55
     of
    0.54
    InputBorder
    0.54
     AssemblyCulture
    0.52
    ⎩
    0.50
    /*:
    0.48
    instead
    0.48
    brainly
    0.48
    Activations Density 0.039%

    No Known Activations