© 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. 45116
    Prev
    Next
    INDEX
    Explanations

    AM

    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
     AM
    -1.11
     
    -1.07
     (
    -1.05
     L
    -1.02
     C
    -1.00
     M
    -0.99
     G
    -0.99
     I
    -0.98
    .
    -0.98
     T
    -0.96
    POSITIVE LOGITS
     myſelf
    2.47
     itſelf
    2.25
     Majefty
    2.23
     raiſ
    2.20
     Efq
    2.16
     Monfieur
    2.14
    ſelves
    2.09
     Jefus
    2.06
    ſelf
    2.05
     Anſ
    2.05
    Activations Density 0.245%

    No Known Activations