© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 77486
    Prev
    Next
    INDEX
    Explanations

    Variations of "go"

    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
     houſe
    -0.90
     HasFactory
    -0.86
     GenerationType
    -0.84
     autorytatywna
    -0.83
    IsMutable
    -0.82
     myſelf
    -0.79
     Signalez
    -0.79
    LookAnd
    -0.79
     Houſe
    -0.77
    Tikang
    -0.77
    POSITIVE LOGITS
     goes
    0.95
     runs
    0.80
    runs
    0.65
    goes
    0.65
     pos
    0.62
     go
    0.60
     went
    0.54
    pos
    0.53
     ran
    0.51
    go
    0.49
    Activations Density 0.001%

    No Known Activations