© 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. 0-CLT-HP
    7. 93903
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    ratt
    -1.56
    bf
    -1.05
    دانشنامهٔ
    -0.65
    interopRequire
    -0.64
    Hochspringen
    -0.61
    Skocz
    -0.60
     برانيه
    -0.58
    printStackTrace
    -0.57
    Datuak
    -0.57
    signol
    -0.56
    POSITIVE LOGITS
     defaultstate
    0.57
    FilterChain
    0.51
    GoogleApiClient
    0.50
    USGS
    0.47
    bcryptjs
    0.45
    lgari
    0.44
    Ranks
    0.42
    ftagPool
    0.42
    ἷ
    0.42
     Munster
    0.41
    Activations Density 0.042%

    No Known Activations