© 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. 11386
    Prev
    Next
    INDEX
    Explanations

    heuristic

    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
    IntoConstraints
    -0.75
     scolaires
    -0.63
    featureID
    -0.62
     GenerationType
    -0.59
    tector
    -0.59
    oa̍t
    -0.58
     policiales
    -0.58
     jambes
    -0.58
     prés
    -0.58
     préférence
    -0.58
    POSITIVE LOGITS
    getValueAt
    0.52
    脚注の使い方
    0.51
     estekak
    0.49
    readString
    0.49
     linearity
    0.48
    Przypisy
    0.46
     surla
    0.46
    Xna
    0.45
    '&:
    0.45
    strerror
    0.45
    Activations Density 0.067%

    No Known Activations