© 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. 4-CLT-HP
    7. 1565
    Prev
    Next
    INDEX
    Explanations

    keep

    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
    ValueStyle
    -0.64
     propOrder
    -0.63
    uarts
    -0.57
    Anhalt
    -0.55
    ="@+
    -0.54
    esModule
    -0.53
    vdots
    -0.52
    AutoScaleMode
    -0.51
    protoc
    -0.51
    tanleria
    -0.51
    POSITIVE LOGITS
     fubject
    0.71
    kies
    0.62
     fufficient
    0.55
     poffible
    0.53
    ió
    0.53
    ,:);
    0.51
    turismo
    0.51
    __.__
    0.50
     gants
    0.50
     Chriftian
    0.49
    Activations Density 0.002%

    No Known Activations