© 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. 4932
    Prev
    Next
    INDEX
    Explanations

    positive descriptions

    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
     muualla
    -0.56
     Wonderful
    -0.55
    Perfect
    -0.50
     wonderful
    -0.50
     perfect
    -0.50
     Perfect
    -0.46
    jamin
    -0.45
     nice
    -0.45
    Wonderful
    -0.44
     sempurna
    -0.43
    POSITIVE LOGITS
     CanadaChoose
    0.76
     betweenstory
    0.75
    ]--;
    0.71
     MessageBoxIcon
    0.71
    aarrggbb
    0.69
    /**
    0.68
     Signalez
    0.65
    ponses
    0.63
     Vikipedi
    0.62
    RuleContext
    0.62
    Activations Density 0.001%

    No Known Activations