Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44828
    Prev
    Next
    INDEX
    Explanations

    nm

    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
    min
    -0.71
    NM
    -0.65
     gal
    -0.59
    gal
    -0.59
     PI
    -0.55
    nm
    -0.53
     min
    -0.51
    PI
    -0.50
     NM
    -0.50
     off
    -0.46
    POSITIVE LOGITS
    LEncoder
    0.84
    OOTDTY
    0.78
     DBNull
    0.76
     AppModule
    0.75
     rendus
    0.74
    🏻‍♀️
    0.73
    })*/
    0.73
    🏼
    0.72
     ")");
    0.71
    '},
    
    0.71
    Activations Density 0.781%

    No Known Activations