© 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. 43992
    Prev
    Next
    INDEX
    Explanations

    Date

    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
    balleur
    -0.77
     nahilalakip
    -0.71
    djangoproject
    -0.69
     BrowserModule
    -0.68
    UnitTesting
    -0.68
    WebVitals
    -0.65
    +#+#
    -0.65
    elux
    -0.65
    EndGlobalSection
    -0.65
     springfox
    -0.64
    POSITIVE LOGITS
    <bos>
    0.94
     aard
    0.51
     ſhould
    0.47
     sympathy
    0.46
     Médico
    0.46
     upgra
    0.44
    I
    0.43
    dealloc
    0.42
     mentale
    0.42
    Yii
    0.41
    Activations Density 0.726%

    No Known Activations