© 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. 5-CLT-HP
    7. 3411
    Prev
    Next
    INDEX
    Explanations

    meat

    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
    >%
    -0.63
    ￡
    -0.52
     témoins
    -0.52
     gants
    -0.51
    mills
    -0.50
    })();
    -0.50
     Surname
    -0.50
    voting
    -0.50
    stackSize
    -0.49
     gradova
    -0.49
    POSITIVE LOGITS
    esModule
    0.51
    TargetException
    0.50
     Italijanski
    0.48
    jects
    0.47
    Примітки
    0.45
    ities
    0.45
    STE
    0.44
    GenerationType
    0.44
    onOptions
    0.44
    Бахар
    0.44
    Activations Density 0.001%

    No Known Activations