© 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. 39896
    Prev
    Next
    INDEX
    Explanations

    video

    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
     NaN
    -0.46
    gola
    -0.42
     munc
    -0.42
     limitée
    -0.41
    to
    -0.41
    pa
    -0.40
    tick
    -0.40
     amoureux
    -0.40
     internacionais
    -0.39
    lag
    -0.38
    POSITIVE LOGITS
    Portale
    0.94
    Personendaten
    0.88
    windowFixed
    0.88
     Audiodateien
    0.86
    Zeneca
    0.86
     GenerationType
    0.85
    KURZBESCHREIBUNG
    0.85
    didSet
    0.85
     Walkover
    0.85
     kaarangay
    0.84
    Activations Density 0.479%

    No Known Activations