© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4523
    Prev
    Next
    INDEX
    Explanations

    slider controls

    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
     capacités
    -0.59
     frattempo
    -0.58
     fourrure
    -0.57
     collègues
    -0.56
     manières
    -0.56
     vectorielles
    -0.55
    RegressionTest
    -0.54
    ContentAsync
    -0.54
     MessageBoxIcon
    -0.54
    aucune
    -0.53
    POSITIVE LOGITS
    DockStyle
    0.53
     BoxFit
    0.52
    Bism
    0.51
     short
    0.48
     a
    0.46
     Parenthood
    0.44
     herd
    0.42
     brief
    0.42
     solvents
    0.40
    bals
    0.40
    Activations Density 0.004%

    No Known Activations