© 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. 1432
    Prev
    Next
    INDEX
    Explanations

    because

    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
    StoreMessageInfo
    -0.65
     ब्रेकडाउन
    -0.54
    Manbalar
    -0.54
    nteral
    -0.52
     للاسماء
    -0.51
     AssemblyCulture
    -0.50
     ffilm
    -0.50
     bì
    -0.49
    estament
    -0.48
    Unmarshal
    -0.48
    POSITIVE LOGITS
     they
    0.64
     there
    0.63
     reasons
    0.62
     it
    0.61
     BoxFit
    0.58
     inferiority
    0.55
    reasons
    0.54
     we
    0.53
     you
    0.52
     interest
    0.52
    Activations Density 0.003%

    No Known Activations