© 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. 4-CLT-HP
    7. 4433
    Prev
    Next
    INDEX
    Explanations

    ase

    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
    InjectAttribute
    -0.79
     pungkas
    -0.69
     saites
    -0.68
    UserScript
    -0.61
     "..\..\
    -0.61
     OFDb
    -0.61
    ukkig
    -0.58
     ☐
    -0.57
    ).\\
    -0.57
     verhe
    -0.57
    POSITIVE LOGITS
    There
    0.47
     (
    0.47
    Because
    0.45
     való
    0.44
    cshtml
    0.44
    I
    0.43
    τας
    0.43
    FetchType
    0.43
    Many
    0.43
    It
    0.43
    Activations Density 0.009%

    No Known Activations