© 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. 38915
    Prev
    Next
    INDEX
    Explanations

    single letters

    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
    H
    -1.37
    M
    -1.34
    D
    -1.34
    L
    -1.34
    G
    -1.28
    R
    -1.27
    B
    -1.26
    T
    -1.25
     
    -1.22
    C
    -1.21
    POSITIVE LOGITS
     itſelf
    1.67
     myſelf
    1.63
     Monfieur
    1.58
     doubtnut
    1.55
     ་་
    1.55
     ―――――
    1.53
    脚注の使い方
    1.52
    ſelves
    1.51
    yntaxException
    1.50
     Efq
    1.48
    Activations Density 0.617%

    No Known Activations