© 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. 38869
    Prev
    Next
    INDEX
    Explanations

    Prior state or history

    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
    lež
    -0.64
    Rhestr
    -0.63
    riwal
    -0.62
    хьтан
    -0.60
     kunde
    -0.56
     gangen
    -0.56
    werd
    -0.56
    who
    -0.55
     HasFactory
    -0.55
     wore
    -0.54
    POSITIVE LOGITS
    <bos>
    1.33
    IUrlHelper
    0.54
    ślę
    0.54
     in
    0.53
    <>());
    0.52
     on
    0.51
     absorbing
    0.50
    dflare
    0.50
    Personendaten
    0.50
     blazing
    0.50
    Activations Density 0.279%

    No Known Activations