© 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. 5-CLT-HP
    7. 5943
    Prev
    Next
    INDEX
    Explanations

    data collection

    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
     BufferedWriter
    -0.62
    athione
    -0.59
    bonucle
    -0.59
    XtraReports
    -0.51
    âteaux
    -0.50
    स्था
    -0.49
     crocodiles
    -0.49
     Erle
    -0.49
    กรณ์
    -0.49
    Data
    -0.48
    POSITIVE LOGITS
     متعلقه
    0.68
    ThroughAttribute
    0.63
    @[+][
    0.55
    ">//
    0.55
    iformis
    0.53
     respeito
    0.52
     passively
    0.52
    ]")]
    0.52
     iprot
    0.50
    oredCriteria
    0.50
    Activations Density 0.003%

    No Known Activations