© 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. 3461
    Prev
    Next
    INDEX
    Explanations

    sp

    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
    StoreMessageInfo
    -0.55
     betweenstory
    -0.54
     Crusoe
    -0.51
    +#+
    -0.50
     filo
    -0.49
    ⓧ
    -0.49
    ğine
    -0.49
    libft
    -0.48
    limus
    -0.48
    opat
    -0.47
    POSITIVE LOGITS
    ContentAsync
    0.72
    rained
    0.67
     esfuer
    0.64
     FetchType
    0.60
     برانيه
    0.59
     symboles
    0.54
    universo
    0.54
    UIN
    0.52
    sonian
    0.52
     câbles
    0.52
    Activations Density 0.004%

    No Known Activations