© 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. 1-CLT-HP
    4. 13012
    Prev
    Next
    INDEX
    Explanations

    writing

    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
     citoy
    -0.67
    LLocation
    -0.63
     envoyer
    -0.60
    ériale
    -0.60
     battre
    -0.60
     publiques
    -0.60
     humaines
    -0.59
     inoxydable
    -0.59
     présidenti
    -0.58
     malheure
    -0.57
    POSITIVE LOGITS
     relative
    0.62
     of
    0.48
    relative
    0.45
     RELATIVE
    0.44
     descriptive
    0.44
     Relative
    0.43
    calciatore
    0.42
    DispatchToProps
    0.41
    transQ
    0.40
    BagLayout
    0.40
    Activations Density 0.003%

    No Known Activations