© 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. 43949
    Prev
    Next
    INDEX
    Explanations

    cozy

    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
    AutoScaleMode
    -0.76
    gebob
    -0.65
    +:+
    -0.65
    CPtr
    -0.60
     تانيه
    -0.59
    ReusableCell
    -0.57
    ceutical
    -0.57
    oa̍t
    -0.55
    kháu
    -0.55
     >=",
    -0.54
    POSITIVE LOGITS
    s
    1.30
    ing
    0.68
    ی
    0.65
    t
    0.64
     Empieza
    0.61
    sent
    0.59
    scri
    0.54
    Personendaten
    0.53
    sS
    0.53
    tling
    0.52
    Activations Density 0.196%

    No Known Activations