© 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. 0-CLT-HP
    7. 95263
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical texts

    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
    ENEFITS
    -0.96
    ITERATURE
    -0.84
    bibfield
    -0.83
    ]='\
    -0.82
    ftant
    -0.80
    IBLIO
    -0.79
    NUMX
    -0.79
    eſ
    -0.79
     defaultstate
    -0.78
     iconFacebook
    -0.78
    POSITIVE LOGITS
    iness
    0.61
    name
    0.59
    sp
    0.58
    str
    0.58
    id
    0.56
    all
    0.56
    ens
    0.56
    ald
    0.55
    enter
    0.54
    one
    0.54
    Activations Density 0.118%

    No Known Activations