© 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. 5-CLT-HP
    4. 1027
    Prev
    Next
    INDEX
    Explanations

    in

    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
    Personensuche
    -0.58
    ScopeManager
    -0.52
    varargin
    -0.49
    EndInit
    -0.49
    Diwedd
    -0.49
    Бахар
    -0.46
    aryen
    -0.46
    kloped
    -0.45
     initComponents
    -0.44
    esgue
    -0.44
    POSITIVE LOGITS
     front
    1.02
     FRONT
    0.81
    Front
    0.80
     Front
    0.77
    styleType
    0.71
    front
    0.70
    FRONT
    0.68
     fronts
    0.66
    ftagPool
    0.62
     frontline
    0.60
    Activations Density 0.003%

    No Known Activations