© 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. 4-CLT-HP
    4. 4583
    Prev
    Next
    INDEX
    Explanations

    code, references

    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
     myſelf
    -1.36
     Efq
    -1.34
     itſelf
    -1.34
    ViewFeatures
    -1.22
    ſelves
    -1.18
     $_"
    -1.16
    ſelf
    -1.15
     himſelf
    -1.12
     Theſe
    -1.12
     themſelves
    -1.10
    POSITIVE LOGITS
    -
    0.93
     
    0.88
    .
    0.72
     "
    0.71
    <strong>
    0.69
     -
    0.69
     “
    0.63
    <b>
    0.61
     a
    0.60
     (
    0.59
    Activations Density 0.000%

    No Known Activations