© 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. 5-CLT-HP
    7. 96156
    Prev
    Next
    INDEX
    Explanations

    spring

    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
    ografi
    -0.47
     boarded
    -0.47
    .
    -0.46
    <bos>
    -0.46
     typology
    -0.45
     aggravating
    -0.45
     instituted
    -0.45
     discharging
    -0.45
    isen
    -0.44
     typ
    -0.44
    POSITIVE LOGITS
    NameInMap
    0.77
    principalTable
    0.73
    XmlAccessorType
    0.73
    RenderAtEndOf
    0.71
     صوتيه
    0.69
     ModelExpression
    0.68
     AssemblyTitle
    0.67
     InputDecoration
    0.67
     AssemblyVersion
    0.66
     فريبيس
    0.65
    Activations Density 0.001%

    No Known Activations