© 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. 1-CLT-HP
    7. 9645
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
     defaultstate
    -0.73
     onOptions
    -0.66
    setScene
    -0.64
    tvguidetime
    -0.60
    roides
    -0.58
     cognition
    -0.57
    ReusableCell
    -0.57
    ConstraintMaker
    -0.56
    </thead>
    -0.56
    OCCURRED
    -0.55
    POSITIVE LOGITS
    InitVars
    0.55
    >",
    0.53
    .},
    0.47
     tartalomajánló
    0.46
    ">'+
    0.46
    department
    0.46
    DEPARTMENT
    0.43
     damper
    0.41
    "}";
    0.41
     department
    0.40
    Activations Density 0.036%

    No Known Activations