© 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. 4-CLT-HP
    7. 3481
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ListItemIcon
    -0.53
    ernoo
    -0.53
    aternion
    -0.49
    AutoScaleMode
    -0.48
    でしたか
    -0.47
    .[/
    -0.46
    ]!='
    -0.45
    verwijspagina
    -0.45
    oneofs
    -0.45
     }}"></
    -0.44
    POSITIVE LOGITS
    OGND
    0.82
    تفصیلات
    0.65
    webElementXpaths
    0.63
    новниш
    0.62
    queness
    0.60
     nakalista
    0.60
     having
    0.59
     wasted
    0.58
     stronger
    0.57
    OwnProperty
    0.57
    Activations Density 0.003%

    No Known Activations