© 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. 5844
    Prev
    Next
    INDEX
    Explanations

    road and place names

    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
    exitRule
    -0.74
    ThroughAttribute
    -0.65
     AllAfrica
    -0.60
     fieldNum
    -0.59
    dirond
    -0.59
    Obrázky
    -0.57
    ytale
    -0.57
    casian
    -0.57
    balleur
    -0.56
     TextInputType
    -0.56
    POSITIVE LOGITS
    andExpect
    0.47
     Creek
    0.45
     Ditch
    0.43
    ValueStyle
    0.43
    ьаж
    0.43
     Wash
    0.41
     Albans
    0.41
     Gulch
    0.41
     Rid
    0.40
    addition
    0.39
    Activations Density 0.001%

    No Known Activations