© 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. 45049
    Prev
    Next
    INDEX
    Explanations

    strength

    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
     strength
    -0.87
     STRENGTH
    -0.75
     Strength
    -0.71
    strength
    -0.71
    Strength
    -0.68
     strengths
    -0.65
     strengthening
    -0.65
     strong
    -0.64
    strong
    -0.63
    Strong
    -0.62
    POSITIVE LOGITS
     المعيارى
    0.88
    XmlAccessType
    0.63
    +#+#
    0.59
    UserScript
    0.59
    getStringExtra
    0.58
    κτηρισ
    0.58
    CastException
    0.57
    enumi
    0.56
     виправивши
    0.56
    SBATCH
    0.56
    Activations Density 0.109%

    No Known Activations