© 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. 10310
    Prev
    Next
    INDEX
    Explanations

    haw

    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
    en
    -0.63
    er
    -0.60
    oma
    -0.51
    y
    -0.47
    esen
    -0.47
    oni
    -0.43
    u
    -0.43
    esi
    -0.43
    చ్
    -0.43
    enha
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    0.84
    InjectAttribute
    0.78
    WaitGroup
    0.76
    CodedInputStream
    0.75
    rrggbb
    0.75
    UnusedPrivate
    0.73
     dAtA
    0.71
    setVerticalGroup
    0.69
    RegistryLite
    0.68
     invokingState
    0.68
    Activations Density 0.010%

    No Known Activations