© 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. 20-CLT-HP
    7. 72896
    Prev
    Next
    INDEX
    Explanations

    code identifiers

    np_max-act-logits · 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
    mira
    -0.44
    trums
    -0.43
    fiers
    -0.42
    })`
    -0.41
     Fingers
    -0.39
     years
    -0.39
     protoimpl
    -0.39
    fingers
    -0.39
    лії
    -0.38
     Tropfen
    -0.38
    POSITIVE LOGITS
     disambiguazione
    1.01
    StoryboardSegue
    0.77
    aarrggbb
    0.74
    DockStyle
    0.73
    ########.
    0.69
     initComponents
    0.68
    AndEndTag
    0.68
    ⓧ
    0.68
    posedge
    0.66
    igshid
    0.65
    Activations Density 0.001%

    No Known Activations