© 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. 5-CLT-HP
    7. 96109
    Prev
    Next
    INDEX
    Explanations

    strive

    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
     TextInputType
    -0.68
    GRANTED
    -0.63
     $_"
    -0.56
     nifer
    -0.55
    ]--;
    -0.55
    localPosition
    -0.54
     StringTokenizer
    -0.54
    Vidite
    -0.54
    naires
    -0.54
     Theſe
    -0.53
    POSITIVE LOGITS
     to
    1.15
     daily
    0.55
     hard
    0.55
     everyday
    0.55
     for
    0.54
    日閲覧
    0.51
    daily
    0.51
    Everyday
    0.50
    everyday
    0.50
    Hard
    0.49
    Activations Density 0.001%

    No Known Activations