© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10946
    Prev
    Next
    INDEX
    Explanations

    }

    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
    politan
    -3.27
    ftagPool
    -0.65
    providedIn
    -0.56
    Попис
    -0.55
    gnąć
    -0.53
    UIControlState
    -0.53
    piac
    -0.51
    piram
    -0.50
    <tbody>
    -0.49
    AddHtmlAttribute
    -0.49
    POSITIVE LOGITS
    AndEndTag
    0.66
    
    0.63
    LEncoder
    0.57
    LLocation
    0.54
    IsContent
    0.54
     AssemblyCompany
    0.50
    EndInit
    0.48
     Sea
    0.48
    didSet
    0.46
    amssymb
    0.46
    Activations Density 0.078%

    No Known Activations