© 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. 91087
    Prev
    Next
    INDEX
    Explanations

    Barber

    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
    omitempty
    -0.80
    Descriere
    -0.59
    Brought
    -0.55
     financeiro
    -0.55
    ouncing
    -0.54
     démocratique
    -0.54
     GoogleFonts
    -0.51
     browser
    -0.50
    DateTimeField
    -0.50
    estination
    -0.48
    POSITIVE LOGITS
     nahilalakip
    0.68
    
    0.59
    steer
    0.55
     ***!
    0.54
    MutableLiveData
    0.54
    StoryboardSegue
    0.53
    }`)
    0.52
    นะครับ
    0.52
     Vecchio
    0.52
    })));
    0.52
    Activations Density 0.217%

    No Known Activations