© 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. 3401
    Prev
    Next
    INDEX
    Explanations

    on

    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
    rungsseite
    -0.63
     onOptions
    -0.61
    classmethod
    -0.57
    httphttps
    -0.56
     nakalista
    -0.55
    Хьажоргаш
    -0.54
    gegangen
    -0.53
    Vidite
    -0.52
     getItemId
    -0.51
    횟
    -0.51
    POSITIVE LOGITS
    VersionUID
    0.53
    tvguidetime
    0.51
     day
    0.48
     which
    0.48
    ukum
    0.46
    gól
    0.46
     تانيه
    0.45
    LIBRARY
    0.45
     front
    0.44
    Strongly
    0.44
    Activations Density 0.002%

    No Known Activations