© 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. 39941
    Prev
    Next
    INDEX
    Explanations

    system solution

    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
    TagMode
    -0.71
     propOrder
    -0.56
    NUMX
    -0.52
    oher
    -0.49
    zerű
    -0.48
    Millisecond
    -0.47
    leggio
    -0.46
     tudom
    -0.45
     Perſ
    -0.44
    IntoConstraints
    -0.43
    POSITIVE LOGITS
    Искәрмәләр
    0.80
     chosen
    0.68
    +#+#
    0.61
     AssemblyCulture
    0.60
    lashed
    0.59
    principalColumn
    0.58
    elemField
    0.57
    SPATH
    0.57
     scelto
    0.57
    IUrlHelper
    0.57
    Activations Density 0.079%

    No Known Activations