© 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. 76871
    Prev
    Next
    INDEX
    Explanations

    reach

    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
    ContentAsync
    -0.66
    دانشنامهٔ
    -0.63
     Spins
    -0.62
    جغرافيا
    -0.62
    DockStyle
    -0.61
     CanadaChoose
    -0.60
     AssemblyCulture
    -0.60
     Référence
    -0.59
    UIControlState
    -0.58
    ❋
    -0.56
    POSITIVE LOGITS
     reach
    1.48
     reaching
    1.45
    reach
    1.25
     reaches
    1.23
     reached
    1.20
     Reaching
    1.19
     Reach
    1.19
    reaching
    1.14
    Reach
    1.13
    Reaching
    1.09
    Activations Density 0.001%

    No Known Activations