© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1576
    Prev
    Next
    INDEX
    Explanations

    mosquitos and vectors

    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
     يتيمه
    -0.63
    \{\\
    -0.60
    IntoConstraints
    -0.58
    kmale
    -0.54
    initializeApp
    -0.53
     rasanya
    -0.52
    товано
    -0.50
    MessageInfo
    -0.50
    AndEndTag
    -0.49
     Yogurt
    -0.48
    POSITIVE LOGITS
     species
    0.52
     distanciation
    0.49
     bite
    0.49
     VARI
    0.48
     Ouverture
    0.48
     bites
    0.46
    ρύ
    0.44
    awtextra
    0.44
    τσα
    0.44
     genus
    0.43
    Activations Density 0.002%

    No Known Activations