© 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. 0-CLT-HP
    7. 97558
    Prev
    Next
    INDEX
    Explanations

    reper

    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
    ulsions
    -0.47
    bors
    -0.46
     Greater
    -0.45
    stasia
    -0.44
    s
    -0.44
     sequences
    -0.43
     lo
    -0.43
    rons
    -0.43
     ass
    -0.42
     disposition
    -0.42
    POSITIVE LOGITS
    RenderAtEndOf
    1.06
     فريبيس
    0.94
    AnchorStyles
    0.84
     beginnetje
    0.77
    SBATCH
    0.77
    ^(@)
    0.75
    κτηρισ
    0.72
     transfieras
    0.72
     صوتيه
    0.72
     NKC
    0.70
    Activations Density 0.085%

    No Known Activations