© 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. 4-CLT-HP
    7. 72
    Prev
    Next
    INDEX
    Explanations

    to

    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
    OrWhiteSpace
    -0.50
     <<<<<<<<<<<<<<
    -0.50
    styleType
    -0.49
    ioutil
    -0.47
    DllImport
    -0.46
    chede
    -0.45
    Eloquent
    -0.43
     separating
    -0.43
    Composable
    -0.43
    separated
    -0.42
    POSITIVE LOGITS
    ReusableCell
    0.76
     an
    0.73
     it
    0.72
     this
    0.68
     a
    0.65
     protoimpl
    0.64
     his
    0.62
    //}
    0.62
     its
    0.61
    endregion
    0.61
    Activations Density 0.001%

    No Known Activations