© 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. 1-CLT-HP
    7. 13176
    Prev
    Next
    INDEX
    Explanations

    random text

    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
    ActionCreators
    -0.57
    usermodel
    -0.46
    EndContext
    -0.45
     GlobalKey
    -0.44
     hæ
    -0.41
    AnchorStyles
    -0.40
     of
    -0.39
    WireFormatLite
    -0.38
     administrative
    -0.38
     Kid
    -0.37
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.75
     chi̍t
    0.68
    허
    0.66
     //$
    0.65
     InputDecoration
    0.65
    modium
    0.61
     Audiodateien
    0.59
    bolt
    0.59
     Himo
    0.59
    orexia
    0.58
    Activations Density 0.023%

    No Known Activations