© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4661
    Prev
    Next
    INDEX
    Explanations

    ul

    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
    FONTE
    -0.46
    izacji
    -0.44
    PLIES
    -0.43
    ETHING
    -0.43
    estic
    -0.43
    giphy
    -0.42
    ERMIN
    -0.42
     Davidson
    -0.42
    rian
    -0.42
    ulfide
    -0.42
    POSITIVE LOGITS
    DockStyle
    0.68
     decorativas
    0.66
    
    0.66
    >
    0.66
    WriteTagHelper
    0.65
     /**
    0.64
    #
    0.63
     phénomènes
    0.63
    /**
    0.61
    mybatisplus
    0.60
    Activations Density 0.010%

    No Known Activations