© 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. 92570
    Prev
    Next
    INDEX
    Explanations

    based

    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
    ]")]
    -0.66
    InputBorder
    -0.51
    ()])
    -0.49
    .")]
    -0.48
    ])).
    -0.47
    omla
    -0.47
    }")]
    -0.46
    ArgsConstructor
    -0.46
     []).
    -0.45
    locke
    -0.44
    POSITIVE LOGITS
    NameInMap
    0.66
     lenker
    0.59
     matière
    0.58
     Baillargeon
    0.58
     materie
    0.57
    chemicals
    0.56
    stånd
    0.56
    featureID
    0.56
    LLocation
    0.56
    material
    0.54
    Activations Density 0.003%

    No Known Activations