© 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. 94983
    Prev
    Next
    INDEX
    Explanations

    Code or scientific descriptions

    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
     الحره
    -0.72
    Hochspringen
    -0.54
    libft
    -0.54
     Trost
    -0.54
    lossians
    -0.53
     requestCode
    -0.49
    +:+
    -0.47
    writeValue
    -0.47
    cinia
    -0.47
    sillon
    -0.45
    POSITIVE LOGITS
    peh
    0.69
     виправивши
    0.65
     morire
    0.54
     useNavigate
    0.53
     Ura
    0.51
     âgées
    0.51
    TargetException
    0.49
    heen
    0.48
     Ged
    0.47
     ura
    0.47
    Activations Density 0.008%

    No Known Activations