© 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. 5-CLT-HP
    4. 95258
    Prev
    Next
    INDEX
    Explanations

    of

    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
     surla
    -0.86
     puissiez
    -0.55
     každ
    -0.52
     nawr
    -0.51
     EVERY
    -0.51
     every
    -0.50
    Iden
    -0.50
     fiecare
    -0.50
     each
    -0.49
    Chaque
    -0.49
    POSITIVE LOGITS
    Kjelder
    0.59
    gares
    0.55
    存于互联网档案馆
    0.54
    penny
    0.54
    adays
    0.54
    λικά
    0.53
     norme
    0.52
    matically
    0.52
    twimg
    0.52
    SequentialGroup
    0.51
    Activations Density 0.002%

    No Known Activations