© 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. 5-CLT-HP
    7. 1163
    Prev
    Next
    INDEX
    Explanations

    problems or topics

    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
     صوتيه
    -0.50
     leash
    -0.50
    NameInMap
    -0.49
    Izvori
    -0.49
    verständlich
    -0.48
    AndEndTag
    -0.47
     mắn
    -0.46
     telefonisch
    -0.46
    EnableWeb
    -0.45
    rrggbb
    -0.44
    POSITIVE LOGITS
     falling
    0.65
     coming
    0.62
    falling
    0.57
    InitVars
    0.54
     Pelo
    0.53
     Италијани
    0.52
    __(/*!
    0.52
     affecting
    0.51
    coming
    0.50
     itali
    0.50
    Activations Density 0.001%

    No Known Activations