© 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. 4347
    Prev
    Next
    INDEX
    Explanations

    Has

    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
    __(/*!
    -0.67
    دانشنامهٔ
    -0.59
    arthed
    -0.57
    atorul
    -0.56
     yawn
    -0.53
    tron
    -0.51
     murales
    -0.50
    եց
    -0.50
    Tweet
    -0.50
     Tujuan
    -0.49
    POSITIVE LOGITS
     estekak
    0.67
    AntiForgeryToken
    0.55
    Ind
    0.48
    MigrationBuilder
    0.47
    EMBLE
    0.45
     TabLayout
    0.44
    MLLoader
    0.44
    __*/
    0.43
    ,:);
    0.43
    hazel
    0.43
    Activations Density 0.017%

    No Known Activations