© 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. 97960
    Prev
    Next
    INDEX
    Explanations

    figure

    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
    resave
    -0.54
    ConstraintMaker
    -0.51
    cinfo
    -0.46
     Schwal
    -0.44
     TestBed
    -0.44
    intern
    -0.43
     prijzen
    -0.43
    wards
    -0.42
     pat
    -0.42
    اخته
    -0.42
    POSITIVE LOGITS
    ngrx
    0.65
    FieldBuilder
    0.64
     تضيفلها
    0.63
     utafitiHapana
    0.60
     BIBSYS
    0.53
    Unified
    0.52
     Unified
    0.52
    %)$
    0.52
    thday
    0.51
    MLLoader
    0.51
    Activations Density 0.002%

    No Known Activations