© 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. 96067
    Prev
    Next
    INDEX
    Explanations

    in

    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
    PMailer
    -0.60
     MotionEvent
    -0.59
    '>";
    -0.57
    IsContent
    -0.54
    ionali
    -0.53
    multicolumn
    -0.53
    ihnachten
    -0.52
    }")]
    -0.52
    Rhestr
    -0.49
    querySelectorAll
    -0.49
    POSITIVE LOGITS
     the
    0.91
     this
    0.67
    Portail
    0.57
    retweeted
    0.57
    this
    0.55
    couverture
    0.55
     этого
    0.55
     tej
    0.55
     этой
    0.54
     этот
    0.52
    Activations Density 0.001%

    No Known Activations