© 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. 92099
    Prev
    Next
    INDEX
    Explanations

    Lambeth

    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
     nakalista
    -0.92
    +#+#
    -0.90
    AndEndTag
    -0.84
    RTEX
    -0.77
     Lordships
    -0.74
     GenerationType
    -0.73
     feroit
    -0.72
    WAUKEE
    -0.72
    appé
    -0.71
     garda
    -0.71
    POSITIVE LOGITS
    iro
    0.57
    mans
    0.57
     Forum
    0.56
     Lid
    0.53
    borne
    0.50
     El
    0.49
     
    0.49
    y
    0.48
     Sen
    0.48
     Phil
    0.48
    Activations Density 0.180%

    No Known Activations