© 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. 38830
    Prev
    Next
    INDEX
    Explanations

    code/file paths/errors

    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
     reject
    -0.60
     SafeMath
    -0.59
    found
    -0.58
    Lähteet
    -0.58
    gram
    -0.55
    tack
    -0.55
    escaping
    -0.55
    sellors
    -0.54
    esc
    -0.53
     rejects
    -0.53
    POSITIVE LOGITS
    aarrggbb
    0.59
    Normdaten
    0.59
    bicara
    0.59
    ]")]
    0.56
    Зноскі
    0.56
    findpost
    0.54
     eorum
    0.53
     habet
    0.51
     îna
    0.50
    XDECREF
    0.50
    Activations Density 0.263%

    No Known Activations