© 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. 4-CLT-HP
    7. 855
    Prev
    Next
    INDEX
    Explanations

    Published

    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
    ThemeOverlay
    -0.60
     umane
    -0.57
    oa̍t
    -0.55
    esgue
    -0.55
    }*/
    -0.54
     ſame
    -0.54
    rungsseite
    -0.54
     ſhould
    -0.53
    }`}
    -0.52
    }*/
    -0.51
    POSITIVE LOGITS
    enumii
    0.65
    الحياه
    0.62
     Mar
    0.57
    : 
    0.55
     mar
    0.53
     saites
    0.52
    errHandler
    0.52
     Nov
    0.50
    findpost
    0.50
     Jul
    0.50
    Activations Density 0.003%

    No Known Activations