© 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. 4873
    Prev
    Next
    INDEX
    Explanations

    Specificity/details

    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
     semplicemente
    -0.50
     őket
    -0.47
    trui
    -0.46
     devriez
    -0.46
     semula
    -0.46
    RefNanny
    -0.45
     presented
    -0.44
     herself
    -0.43
     kasarigan
    -0.42
     suffit
    -0.42
    POSITIVE LOGITS
     there
    0.99
    ,
    0.86
     it
    0.82
    ReusableCell
    0.76
    IntoConstraints
    0.73
     we
    0.68
    AndEndTag
    0.65
    there
    0.65
    StoryboardSegue
    0.65
    providedIn
    0.64
    Activations Density 0.001%

    No Known Activations