© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92059
    Prev
    Next
    INDEX
    Explanations

    versions

    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
     itſelf
    -1.18
     models
    -1.10
     formats
    -1.10
     myſelf
    -1.09
     versions
    -1.06
     Theſe
    -1.05
     ſche
    -1.04
     Jefus
    -0.98
     styles
    -0.96
    ſelf
    -0.92
    POSITIVE LOGITS
     of
    0.67
     for
    0.64
     are
    0.63
    .
    0.63
    ,
    0.61
     and
    0.60
     were
    0.58
     in
    0.54
     lèvres
    0.54
    <eos>
    0.53
    Activations Density 2.151%

    No Known Activations