© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97544
    Prev
    Next
    INDEX
    Explanations

    separation processes

    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
     split
    -0.92
    bled
    -0.87
     rid
    -0.84
    atization
    -0.81
    split
    -0.65
     فريبيس
    -0.63
     Roskov
    -0.62
     Efq
    -0.60
    roppo
    -0.59
    oarece
    -0.59
    POSITIVE LOGITS
     ***!
    0.52
    oluble
    0.50
    TintMode
    0.47
    ########.
    0.45
    WriteBarrier
    0.44
    +#+
    0.44
    lapsingToolbar
    0.43
    启
    0.43
    gameserver
    0.43
     des
    0.42
    Activations Density 0.671%

    No Known Activations