© 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. 97649
    Prev
    Next
    INDEX
    Explanations

    checkpoints

    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
     Efq
    -1.36
     Majefty
    -1.27
    ſelf
    -1.25
     itſelf
    -1.24
     themſelves
    -1.23
     purpoſe
    -1.21
     Houſe
    -1.20
     myſelf
    -1.19
     Monfieur
    -1.18
     Shakspeare
    -1.17
    POSITIVE LOGITS
     
    0.71
     ra
    0.68
     nu
    0.64
    ,
    0.64
     en
    0.63
    ing
    0.60
     van
    0.60
     in
    0.60
     (
    0.60
     ir
    0.59
    Activations Density 0.134%

    No Known Activations