© 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. 43981
    Prev
    Next
    INDEX
    Explanations

    Types, descriptions, classifications

    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
    HideFlags
    -0.74
     scoperta
    -0.66
    HttpDelete
    -0.61
    Jereo
    -0.60
    resave
    -0.60
     TextInputType
    -0.59
    BufferException
    -0.58
    antaranya
    -0.58
     UserDao
    -0.58
     dismissal
    -0.57
    POSITIVE LOGITS
    ic
    0.67
    el
    0.54
    iac
    0.53
     lenker
    0.49
    ia
    0.47
    izer
    0.46
    im
    0.46
    ści
    0.46
    on
    0.46
    ist
    0.46
    Activations Density 0.175%

    No Known Activations